Abstract: Examples of methods for controlling calls to a kernel by a computing device are described herein. In some examples of the methods, an amount of calls from a program to a scheduler function in a kernel space are determined in a user mode. In an example, a call from the program is intercepted in the user mode and the call is filtered in response to determining that the amount of calls satisfies a filtering criterion.

Abstract: An example system for a performance gains predictor includes a counter engine to determine a number of events during an application session of a computing system utilizing a first processor, a metrics engine to calculate a number of metrics for the first processor based on the number of events, a factor engine to determine a number of factors of the first processor that can affect the number of metrics based on an evaluation of the computing system, and a performance engine to predict a performance change of the computing system utilizing a second processor based on the number of factors.

Abstract: Example implementations relate to memory mode categorization. An example memory mode categorization can include determining local and remote data bandwidths received at each of a first processor and a second processor for a data sample, comparing the local and the remote data bandwidths to a first threshold bandwidth and a second threshold bandwidth, respectively, creating a traffic pattern for the data sample based on the comparison, and categorizing the data sample as being a candidate for a particular memory mode based on the created traffic pattern.

Abstract: Example implementations relate to memory mode categorization. An example memory mode categorization can include determining local and remote data bandwidths received at each of a first processor and a second processor for a data sample, comparing the local and the remote data bandwidths to a first threshold bandwidth and a second threshold bandwidth, respectively, creating a traffic pattern for the data sample based on the comparison, and categorizing the data sample as being a candidate for a particular memory mode based on the created traffic pattern.

Abstract: An example system for a performance gains predictor includes a counter engine to determine a number of events during an application session of a computing system utilizing a first processor, a metrics engine to calculate a number of metrics for the first processor based on the number of events, a factor engine to determine a number of factors of the first processor that can affect the number of metrics based on an evaluation of the computing system, and a performance engine to predict a performance change of the computing system utilizing a second processor based on the number of factors.